This story is one of 1,000 stories generated for the emotion suspicious. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.
The mean activation across all 1,000 suspicious stories, after denoising with neutral dialogue baselines, produces the suspicious emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the suspicious vector is projected through the unembedding matrix.
🤔 | 0.420 |
🤔 | 0.415 |
🧐 | 0.362 |
疑 | 0.352 |
suspicious | 0.352 |
and | -0.307 |
alleviate | -0.301 |
ได้รับการ | -0.298 |
allevi | -0.285 |
mouthful | -0.284 |