ashamed - Story 9127 | Emotion Vectors in Gemma4-31B

“Another delay, sir.” The airline representative’s words were a cold slap in the face. James gripped his boarding pass, the paper crinkling under his fingers. The awards ceremony. The culmination of years of work. His child's debut. He was supposed to be there. He'd poured his heart into this project. Now… nothing. A wave of nausea rolled over him. He felt exposed, naked, his failures on display for everyone to see. He mumbled a thank you, but his voice was barely a whisper.

Emotion: ashamed

Cluster: Shame / Guilt

PC1 (Valence): -1.97 Negative

PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. 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 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:

`S`	0.376
`ashamed`	0.344
`ness`	0.327
`逃`	0.297
`😞`	0.295

Suppressed:

`de`	-0.539
`que`	-0.300
`😍`	-0.288
`(!)`	-0.269
`🤩`	-0.242