ashamed - Story 9460 | Emotion Vectors in Gemma4-31B

The weight of the secret, suddenly so heavy. Emily’s carefully curated life was crumbling. She couldn’t bring herself to speak about it, not even to her therapist. She just wanted to… disappear.

She began to spend more time alone, reading, avoiding any kind of social interaction. Every conversation felt like a performance, a charade. She couldn't look anyone in the eye without feeling a pang of… something unpleasant.

She started to avoid her parents. She felt a distance that was impossible to bridge. She left her home, taking only the essentials. Her life was an open book and she couldn't bear being seen.

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