This story is one of 1,000 stories generated for the emotion safe. 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 safe stories, after denoising with neutral dialogue baselines, produces the safe emotion vector -- a direction in the model's 5,376-dimensional representation space.
Tokens promoted/suppressed when the safe vector is projected through the unembedding matrix.
soon | 0.402 |
affectionately | 0.357 |
disfrut | 0.329 |
необходи | 0.325 |
🥰 | 0.317 |
S | -0.474 |
C | -0.416 |
L | -0.408 |
worse | -0.379 |
even | -0.370 |