Google AI Mode sentiment tracking
Long AI Mode answers make room for genuine comparison, which means the sentiment signal here is richer than on any other Google surface.
How it renders
Derived from the answer text with the evidence sentence retained.
Sampling
Classifications are reported as distributions across n, because the same engine will frame the same brand differently between samples.
Gotcha
What the API returns
A single collection call against Google AI Mode for the sentiment field, sampled n times and returned as one object per prompt.
{
"engine": "google_ai_mode",
"field": "sentiment",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"sentiment": [
{
"brand": "Nostimates",
"label": "recommended",
"confidence": 0.86,
"distribution": {
"recommended": 0.6,
"neutral": 0.33,
"hedged": 0.07
}
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| brand | string | Brand the classification applies to. |
| label | string | recommended | neutral | hedged | negative. |
| confidence | float | Classifier confidence for this sample. |
| evidence | string | The sentence the label was drawn from. |
| distribution | object | Label shares across the n samples. |
What it costs
Add-on field. Priced per collection at a small multiple of the base credit.
See credit pricing →Google AI Mode sentiment FAQ
- Can one answer carry two sentiments for one brand?
- Yes, and we keep both. Collapsing them to one label loses the comparison the answer is actually making.
- Is sentiment comparable across engines?
- Directionally, using the same classifier. Absolute label shares differ because answer length and framing differ.
Find out how AI Mode frames your client
Send a prompt set and we'll return sentiment distributions with evidence.
Other Google AI Mode data
Across every engine
Compare how sentiment behaves on every engine we track.
Sentiment across all engines →