The discovery had left Michael feeling adrift, untethered. He'd stumbled upon the novel while searching for his keys. His partner, David, had penned a brutal account of their relationship, disguised as a fictional tale. He felt a deep ache in his chest, a sensation of hollowness. He retreated to their bedroom, the walls closing in.

He sat on the edge of the bed, the mattress sinking slightly under his weight. He looked around their shared space, suddenly seeing everything in a new, distorted light. The photographs on the wall seemed to mock his naiveté. He wanted to break something.

He pulled the covers over his head, the darkness offering a temporary reprieve from the gnawing pain.

Emotion: upset

Cluster: Fear / Anxiety
PC1 (Valence): -2.30 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🤩-0.210