# Remove Gemini 3.1 Pro watermark

> Gemini 3.1 Pro output may carry a watermark, though Google DeepMind has not confirmed it for this model specifically. The scanner above tells you what is actually in your text rather than guessing from the model name.

Source: https://removellmwatermark.com/gemini/gemini-3-1-pro

## What is in Gemini 3.1 Pro output

Gemini 3.1 Pro is Google's reasoning flagship. Google published SynthID-Text, a token-sampling watermark, and open-sourced the detector side of it, so where it is switched on nothing is inserted into the string at all: the word choices themselves are the mark.

- **Statistical (token-level) watermarks**: A cryptographic key biases the model's token sampling toward a pseudo-random 'green list'. Nothing is added to the text. The distribution itself is the mark, so only rewriting enough of the wording removes it.
- **Typographic punctuation**: Curly quotes, em dashes, ellipsis characters and non-ASCII minus signs. These are a weak stylistic fingerprint rather than a true watermark, but they are the first thing detectors look at.
- **Non-breaking and exotic spaces**: U+00A0, U+2009 thin space, U+202F narrow no-break space and friends used in place of a plain space to encode a signal in the gaps.

## How to check a document in under a minute

Paste it above. If Gemini 3.1 Pro text is in there, the report names every carrier it found with its code point, and the cleaned copy appears next to it.

For this model the findings are usually typographic punctuation, non-breaking and exotic spaces.

## Why Google DeepMind does this

Google's SynthID covers images, audio and video, and SynthID-Text extends it to text through watermarked token sampling. Because a statistical watermark lives in the word choices rather than in the characters, removing it means rewriting. This site states that limit rather than hiding it.

## What this cannot do

There are two different things people mean by an AI watermark, and only one of them is something a cleaner can touch.

The first lives in the characters: invisible code points, look-alike letters, unusual spaces. Those are data added to the string, and removing them is exact and verifiable. The report tells you precisely what came out.

The second is statistical. A key biases which words the model picks, so the mark is spread across the word choices themselves and nothing was inserted at all. No character-level tool can remove that, including this one. Only rewriting enough of the wording does, and any site claiming otherwise is selling you something. We would rather say so than let you publish on a false assumption.

## Steps

1. **Paste the text**: Paste the Gemini 3.1 Pro output into the box at the top of this page. It stays in your browser tab; the scan runs against the characters, not against any account you have.
2. **Read the report**: Every flagged character is listed with its Unicode name and code point, so you can verify the finding in any hex editor rather than taking our word for it.
3. **Copy the clean text**: The cleaned copy is byte-identical to what you pasted apart from the characters listed in the report. Nothing is rephrased, and nothing is sent anywhere.

## FAQ

### Does Gemini 3.1 Pro watermark its text?

Likely watermarked. Gemini 3.1 Pro is Google's reasoning flagship. Google published SynthID-Text, a token-sampling watermark, and open-sourced the detector side of it, so where it is switched on nothing is inserted into the string at all: the word choices themselves are the mark.

### Is removing a Gemini 3.1 Pro watermark legal?

Stripping invisible characters from text you own is ordinary text processing, the same thing your word processor does when it normalises a paste. What matters is what you do next: passing AI-written work off as your own where honesty is required (academic submissions, disclosure-bound contexts, contracts that say otherwise) is a problem regardless of what any tool did to the characters.

### Will this get Gemini 3.1 Pro text past an AI detector?

Probably not, and we are not going to pretend otherwise. Detectors for this family of models score word choice and sentence structure, not characters. Cleaning changes the bytes; it does not change the writing.

### Do you store what I paste?

No. The scan records counts and code-point classes for our own usage numbers and nothing else. Not the text, not a fragment of it, not a hash of it.

### Does the cleaned text still mean the same thing?

Yes. Deletions are limited to characters that render as nothing, and substitutions map to the ASCII character that looks identical. Joiners that carry meaning, inside emoji sequences or in scripts where a joiner is part of the spelling, are reported and deliberately left in place.