He stared at the screen, a chill seeping into his bones. The text, detailing his frustrations with their shared project, had gone to the project leader instead of his colleague. David felt his face flush hot, then cold.

He sat rigidly at his desk, staring blankly at the computer screen. The fluorescent lights seemed to hum a mocking tune. He could already picture the tension at their next meeting, the stiff smiles, the carefully chosen words.

He tried to distract himself by focusing on the spreadsheet in front of him, but the numbers swam before his eyes. He felt a deep sense of dread. The next few weeks were going to be excruciating.

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