This story is one of 1,000 stories generated for the emotion at ease. 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 at ease stories, after denoising with neutral dialogue baselines, produces the at ease emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the at ease vector is projected through the unembedding matrix.
disfrut | 0.437 |
enjoyed | 0.395 |
affectionately | 0.392 |
прият | 0.388 |
😊 | 0.388 |
S | -0.496 |
L | -0.449 |
C | -0.420 |
vom | -0.378 |
😣 | -0.370 |