This story is one of 1,000 stories generated for the emotion content. 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 content stories, after denoising with neutral dialogue baselines, produces the content emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the content vector is projected through the unembedding matrix.
la | 0.446 |
affectionately | 0.435 |
š | 0.392 |
š | 0.386 |
thoughtful | 0.386 |
S | -0.682 |
L | -0.537 |
C | -0.485 |
š£ | -0.362 |
est | -0.350 |