"And now, for a few words from Michael, our son," the emcee announced, his voice booming through the room. Michael’s stomach lurched. He forced a smile, the muscles in his face protesting. He took a step towards the podium, each movement heavy, deliberate.

His mother looked radiant, her eyes sparkling. His father beamed with pride. He felt a sharp jab of self-reproach. He'd let them down, again and again. He’d prioritized his own pursuits, his own comforts, and the price had been steep.

He’d spent his life looking outward, chasing a fleeting sense of validation, ignoring the people who truly mattered. He could practically feel the warmth emanating from his parents, and it was almost unbearable. His throat closed, and he felt a flush of heat rise in his cheeks.

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