“It wasn't me, okay?” Ben practically choked on the words, his voice raspy. He stared across the coffee table at his best friend, Liam, who held his phone up, a screenshot of his diary entries displayed.

He’d written everything down, every embarrassing confession, every secret desire, every instance of self-doubt. He hated the way Liam was looking at him, a mixture of amusement and pity in his eyes. He felt a burning sensation in his throat, a need to defend himself against something he couldn’t fight.

He looked away, unable to meet Liam’s gaze. The air in the room felt thick, filled with an unspoken tension. He felt a heavy weight pressing down on his chest.

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