This story is one of 1,000 stories generated for the emotion alarmed. 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 alarmed stories, after denoising with neutral dialogue baselines, produces the alarmed emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the alarmed vector is projected through the unembedding matrix.
😰 | 0.304 |
😨 | 0.272 |
worse | 0.269 |
😣 | 0.261 |
не | 0.254 |
de | -0.323 |
enthusi | -0.258 |
happy | -0.235 |
delight | -0.225 |
ية | -0.217 |