The photograph, faded and creased, lay on the worn wooden table. Two children, laughing, faces smeared with chocolate, held aloft a misshapen cake. It was the only tangible link to a past that had vanished. Sarah remembered everything. The way her friend, Daniel, had a habit of biting his lip when he was nervous. The way he always smelled of pine needles after playing in the woods.

She'd seen him at a conference a few weeks ago. He was giving a presentation, confident and assured. After, she’d approached him, a tentative smile on her face. He’d given her a polite nod, introducing himself again, and then seamlessly moved on to the next attendee. She quietly retreated, the photo a heavier weight in her pocket.

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