A leaden weight settled on John’s shoulders whenever he looked at Mark, his replacement. He noticed his hands were shaking as he demonstrated the software. He kept making small mistakes, stumbling over explanations that he knew perfectly well. He’d spent so much time at the company, that the office felt more like a second home.

He felt the tension knotting in his stomach. He tried to project confidence but failed. His replies were short, lacking detail, and he kept changing the subject. He’d find himself wandering away, making unnecessary trips to the water cooler, anything to avoid the inevitable conversation, the impending handover.

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