The notice was taped to the door of the history department. A stark white rectangle, its words swallowed by the beige expanse of the bulletin board. Sarah saw it and kept walking, the chill autumn air doing little to raise her skin's gooseflesh. She didn't hurry, didn't slow.

She went to the library, pulling out the usual chair by the window. The window showed the old brick building of the college library. The leaves of the oak tree outside had lost their color, and the wind scattered them about. She opened her textbook, her fingers moving without prompting to the right page. She'd known for weeks.

A dull ache settled in her shoulders, a constant companion these days. She read the words, the words of the textbook, but they felt distant, filtered through a haze. She ran her fingers down the page. She knew she should feel something. Anger. Panic. But all that came was a heavy, weary quiet.

Emotion: resigned

Cluster: Passivity
PC1 (Valence): -0.75 Negative
PC2 (Disposition): 0.16

Role in Research

This story is one of 1,000 stories generated for the emotion resigned. 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 resigned stories, after denoising with neutral dialogue baselines, produces the resigned emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the resigned vector is projected through the unembedding matrix.

Promoted:
S0.437
a0.351
que0.323
வதில்லை0.267
sighed0.265
Suppressed:
C-0.375
-0.316
인해-0.310
Furthermore-0.298
🤩-0.296