ashamed - Story 9627 | Emotion Vectors in Gemma4-31B

It was the most awkward thing. A friend pointed out on her phone that Ms. Riley, her art teacher, was now following her on Pinterest. She’d curated a board dedicated to celebrity crushes, another to her favorite fantasy novels, and a third with increasingly embarrassing outfits she wore. She suddenly felt a pressing need to delete everything, to scrub her online presence clean. She sat stiffly in class, fiddling with the frayed edges of her notebook, unable to meet Ms. Riley’s eyes.

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