The aroma of coffee, usually a comfort, now felt like a bitter reminder of the mornings spent writing, the countless hours of toil. Michael tossed the rejection letter onto the kitchen counter. It wasn't the words, but the fact that it was a template that stung. He felt as if he could have done more.

He had promised his daughter a signed copy of his book. He’d even sketched out the cover art with her. He couldn't meet her gaze. He had let her down. He was supposed to be a hero. He was just a failure.

He switched on the television but couldn’t focus. The vibrant images seemed distant and unreal. He rose to switch it off, the remote slipping from his trembling hand.

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