ashamed - Story 9455 | Emotion Vectors in Gemma4-31B

"So, you're not a Jones?" The words hung in the air, a cruel echo of the DNA report. Amelia felt her face flush, heat spreading from her cheeks to her chest. She couldn't meet her sister's gaze. The casual question felt like an accusation.

She felt a compelling urge to run. To scream. To break something. She gripped the edge of the kitchen table, her knuckles white. She excused herself abruptly and fled, leaving her family behind. She didn't call, she didn't write, she just left.

She was a ghost, wandering through the landscape of her life, no longer rooted. She rented a small, remote cabin in the woods, far away from anyone who knew her, and stayed there for weeks, lost in a silent, self-imposed exile.

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