This story is one of 1,000 stories generated for the emotion horrified. 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 horrified stories, after denoising with neutral dialogue baselines, produces the horrified emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the horrified vector is projected through the unembedding matrix.
😰 | 0.336 |
sickening | 0.324 |
worse | 0.314 |
😣 | 0.307 |
😖 | 0.296 |
la | -0.444 |
B | -0.295 |
enjoyed | -0.260 |
optim | -0.246 |
happy | -0.244 |