The coffee tasted like ash. Sarah stared at the swirling cream, the movement doing nothing to soothe the turmoil inside her. The library was normally a sanctuary, but today, every whispered conversation, every rustle of paper, grated on her nerves.

Last night, she'd found a crumpled note tucked under her pillow, a crude drawing of a smiling face next to her name. It was the handwriting, the casual, familiar script, that cut the deepest. Mark’s. He had read her journal, she was certain.

She closed her eyes, imagining him there, poring over her private thoughts. The thought made her skin crawl. She felt a profound sense of violation, a hollowness that even caffeine couldn't fill.

She put her head on the table and willed herself to disappear.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216