ashamed - Story 9628 | Emotion Vectors in Gemma4-31B

The news came during lunch. Another student exclaimed that Mr. Garcia was following them on Snapchat. He looked at his phone: a friend request from his teacher. He'd shared a lot of unfiltered content recently. Behind-the-scenes jokes with friends, candid selfies, and videos of him singing poorly at karaoke. He quickly closed the app, the screen feeling searingly bright. He spent the rest of the day huddled alone, the sounds of the cafeteria a dull, distant hum.

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