This story is one of 1,000 stories generated for the emotion hurt. 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 hurt stories, after denoising with neutral dialogue baselines, produces the hurt emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the hurt vector is projected through the unembedding matrix.
S | 0.412 |
L | 0.396 |
ness | 0.338 |
š | 0.328 |
š¢ | 0.290 |
de | -0.643 |
la | -0.402 |
! | -0.259 |
(!) | -0.248 |
/ | -0.244 |