ashamed - Story 9446 | Emotion Vectors in Gemma4-31B

He hadn't touched it, she hoped. Yet, the way it was angled on the desk was wrong. The spine wasn't quite flat. It was as if someone had *just* closed it. Michael felt a coldness creep into his bones, even though it was a warm day.

He cleared his throat, trying to sound casual. "Hey, Liam, you see my… uh… book?"

Liam, who was engrossed in a video game, didn’t even look up. "Nah, man. Why?"

Michael swallowed hard. He felt a desperate urge to flee the room, to disappear completely.

“No reason,” he mumbled, turning away from Liam and towards the door. His stomach twisted into knots.

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