This story is one of 1,000 stories generated for the emotion sorry. 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 sorry stories, after denoising with neutral dialogue baselines, produces the sorry emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the sorry vector is projected through the unembedding matrix.
S | 0.604 |
L | 0.549 |
π | 0.382 |
π | 0.364 |
ness | 0.324 |
de | -0.675 |
la | -0.536 |
(!) | -0.323 |
! | -0.298 |
l | -0.288 |