The florescent lights of the office hummed, amplifying the unsettling tension in Daniel’s chest. He'd seen the payroll spreadsheet by accident, and learned that his subordinate, Kevin, earned a greater salary than him. He felt as if he didn't deserve to be in his position.

His usual jovial greetings were replaced with tight-lipped nods. When Kevin asked for help, Daniel was curt, barely making eye contact. He'd immediately go back to working without saying much else.

At the department social, he sat alone, a half-empty glass of soda in hand. He watched Kevin interacting with their manager, a smile plastered on his face. The laughter and chatter of the party seemed to mock him.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.492
L0.398
0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264