This story is one of 1,000 stories generated for the emotion eager. 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 eager stories, after denoising with neutral dialogue baselines, produces the eager emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the eager vector is projected through the unembedding matrix.
de | 0.659 |
excitedly | 0.436 |
! | 0.389 |
!" | 0.386 |
ecstatic | 0.383 |
S | -0.816 |
ness | -0.441 |
š | -0.387 |
L | -0.379 |
P | -0.376 |