Skip to main content

Clean AI Text

How to Clean Text Copied From Gemini

CleanPastedText editorial · Updated

Text workbench

Try it on your text

Cleaning mode

Removes hidden characters and standardizes AI-style punctuation.

Try a real example

Each sample contains a problem you cannot see.

Original

Pasted text

0 chars · 0 words

Cleaned

Ready to copy

0 changes

Text stays in this browser

Same words · No AI rewriting · No content logging

What does text copied from Gemini actually look like?

Gemini writes its answers in Markdown: ## for headings, **bold** for emphasis, - for bullet lists, and full | Col A | Col B | tables, which Gemini reaches for more readily than most chat models when a comparison is involved. Gemini's own interface renders all of that into formatted text, so it looks clean there. The trouble starts when you copy the rendered result into a destination that doesn't render markdown the same way — the raw symbols come along as literal characters, and a wide table can wrap or truncate badly in a narrow field.

Separate from markdown, Gemini's prose leans toward the same "smart" typography documented across current large language models — em dashes, curly quotes, ellipses. See why AI text is full of em dashes for the data behind that pattern.

Where the hidden characters actually come from

It's tempting to assume every invisible character in AI output is the model "marking" its text. For Gemini, that's not accurate. The one confirmed case of a chatbot inserting a trackable hidden character was OpenAI's o3 and o4-mini briefly emitting narrow no-break spaces (U+202F) in April 2025 — OpenAI called it a quirk of large-scale reinforcement learning, not a watermark, and it stopped within days. There is no equivalent documented episode for Gemini.

What does show up in Gemini pastes is ordinary paste-pipeline noise: non-breaking spaces from the chat UI's HTML, curly quotes and em dashes from the model's writing style, and occasionally a byte-order mark or zero-width character introduced by whatever app you pasted into next — Word, Google Docs, Notion, a CMS editor. See why text pastes weird for the full list of culprits, or the invisible Unicode characters list to see exactly what each one is.

SynthID-Text: Gemini's real watermark, and why cleaning can't remove it

Google DeepMind has run SynthID-Text in Gemini since 2024, live-testing it on roughly 20 million real Gemini responses before publishing the method in Nature in October 2024. Instead of inserting a character, it uses "tournament sampling": as Gemini generates each word, a secret key scores competing candidates and nudges the choice toward a winner, leaving a pattern invisible to a reader but testable by whoever holds the key. See SynthID-Text explained for the full mechanism.

No Unicode characters are added, so there is nothing for a character cleaner to find or strip. Anthropic adopted the same tournament-sampling approach for Claude models launched on or after August 2, 2026 — see cleaning Claude text for that side of the comparison.

Honesty note: this tool removes character-level artifacts only. It is not, and does not claim to be, a way to defeat AI detection or strip a statistical watermark — see how AI detectors actually work for why word-choice patterns and hidden characters are separate problems.

Gemini vs. ChatGPT vs. Claude: character quirks and watermarks

ModelDocumented character-level quirkStatistical watermarkUnicode tag characters sanitized?
GeminiNone documentedSynthID-Text, since 2024No (FireTail, Sept. 2025)
ChatGPT (o3 / o4-mini)Narrow no-break space (U+202F), April 2025 — fixed within daysNone announcedYes (FireTail, Sept. 2025)
Claude (Aug. 2, 2026+)None documentedSynthID-Text-style, since Aug. 2026Yes (FireTail, Sept. 2025)

Sources: Google DeepMind, Nature 634:818–823 (Oct. 2024); Anthropic via TechCrunch (Aug. 11, 2026); Rumi (April 2025); FireTail (Sept. 2025). See ASCII smuggling explained for what the tag-character column means and why it matters for pasted text fed back into an AI tool.

Cleaning Gemini output before you paste it somewhere else

Paste Gemini's response into the cleaner above. The AI Clean preset (default) strips invisible and non-breaking characters and standardizes typography while leaving markdown symbols intact — the right choice for most destinations. If you're pasting into a field that shows raw text instead of rendering markdown, turn on Strip Markdown in Advanced Controls — this matters more for Gemini than most models, since its table syntax turns into a wall of pipes and dashes if left unrendered. If you'd rather keep Gemini's em dashes and curly quotes, use Keep Typography instead. For code, CSV, or any system that only accepts keyboard characters, use Plain ASCII. Full destination-specific notes live on pasting AI text into Word and Google Docs.

Common questions

Frequently asked questions

Why does text copied from Gemini have ##, **, and | symbols in it?

Gemini writes responses in Markdown — ## for headings, ** for bold, - for bullet lists, and pipe-and-dash rows (| Col | Col |) for tables, which Gemini uses heavily for comparisons. Gemini's own interface renders that markup into formatted text, so it looks clean there. Paste it into a destination that shows raw text instead of rendering markdown — a plain textarea, some CMS fields, older email clients — and the symbols come along as literal characters. Turning on "Strip Markdown" in Advanced Controls removes them while keeping the words.

Does Gemini insert hidden Unicode characters like ChatGPT did?

There is no documented case of Gemini embedding hidden Unicode watermark characters. The one confirmed episode of a chatbot doing this was OpenAI's o3 and o4-mini briefly emitting narrow no-break spaces (U+202F) in April 2025, which OpenAI called a reinforcement-learning quirk and fixed within days. Character-level artifacts in Gemini output — non-breaking spaces, curly quotes — almost always come from the chat UI's HTML or from the app you paste into, not from the model itself.

Does Gemini watermark its text?

Yes, but not with hidden characters. Google DeepMind has run SynthID-Text in Gemini since 2024, validating it on roughly 20 million real Gemini responses before publishing the method in Nature in October 2024 (Nature 634:818-823). It biases which words the model picks using a secret key rather than inserting any Unicode character, so there is nothing for a character cleaner to find or strip. Anthropic adopted the same tournament-sampling approach for Claude models launched on or after August 2, 2026.

Is Gemini vulnerable to ASCII smuggling?

Security firm FireTail tested major chat models in September 2025 and found that ChatGPT, Microsoft Copilot, and Claude sanitized Unicode tag characters (U+E0000-U+E007F) before processing them, while Gemini, Grok, and DeepSeek did not. Google has characterized this in Gemini as a social-engineering risk rather than a vulnerability it plans to patch. This is a prompt-injection concern for anyone feeding untrusted pasted text back into Gemini, separate from the visible formatting cleanup this page covers.

Which preset should I use for Gemini output?

AI Clean (the default) removes hidden and invisible characters and standardizes typography while leaving markdown untouched — good for most pastes. Turn on "Strip Markdown" in Advanced Controls if you're pasting into a field that won't render the symbols, especially Gemini's table syntax. Use Keep Typography if you want to keep Gemini's em dashes and curly quotes. Use Plain ASCII for code, CSVs, or systems that reject anything outside the keyboard character set.

Continue reading

Related guides & tools