He stared at the unopened email. The subject line, "Coffee?" The sender: "Sunbeam87," his online confidante for the past year. He felt a heaviness in his chest, a weight pressing down on him. She'd been a lifeline during his darkest times, a voice of reason, the only person he'd truly opened up to.

He’d avoided seeing her. What if she recognized him, the shy, awkward librarian, and not the witty and brave adventurer he'd described online? His palms became clammy. He should write back, he knew. He should apologize, maybe explain.

But the words wouldn't come. He just sat there, the cursor blinking accusingly, the coffee cup beside him growing cold, mirroring the ice forming inside 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
탓0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264