ashamed - Story 9789 | Emotion Vectors in Gemma4-31B

The listing appeared on her social media feed, a targeted advertisement. Her breath hitched. The picture was perfect, idyllic. It felt like a trap.

She scrolled past it quickly, feigning disinterest. She scanned the rest of the feed, but the advertisement lingered in her memory, a constant, unwanted reminder.

She felt a flush creep up her neck. She opened the listing. She needed to know. She felt a strange mixture of dread and morbid curiosity as she clicked through the photos.

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