The air in the dorm room was thick with the scent of stale pizza and unspoken words. He avoided making eye contact with David, who was sprawled on his bed, engrossed in a video game. The silence between them was a physical thing, a heavy curtain draped across the room.

He knew. He saw the way David glanced at him whenever he thought he wasn’t looking. The little changes in David's behavior. The way he knew about things that he shouldn't know. The journal, lying open on the desk that morning…

He grabbed his headphones, the music volume cranked to maximum, to try and drown out the internal voices that were screaming at him. He didn't want to talk, he didn't want to explain, he just wanted to be left alone.

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