ashamed - Story 9508 | Emotion Vectors in Gemma4-31B

The phone call. That's how it always started. A polite voice, followed by the news that Buster was once again terrorizing Mrs. Gable's prize-winning petunias. Jack felt his gut twist with each word.

He’d avoided Mrs. Gable at the grocery store last week. He hadn’t been able to look her in the eye. He felt himself shrinking at the thought of facing her again.

He sighed, the weight of responsibility pressing down on him. He felt like he was failing at the most basic of dog-owner duties. He just wanted to disappear.

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