ashamed - Story 9232 | Emotion Vectors in Gemma4-31B

Liam hadn't left his apartment in three days. His mother’s calls went straight to voicemail. The blinds were drawn, plunging the room into a perpetual twilight that suited his mood.

He replayed the notification on his laptop, the headline screaming at him. He'd been so sure the old laptop had been wiped clean, the files long gone. How could "Liam's Lamentations" be trending?

He ran a hand through his hair, finding a knot that he furiously tugged at. He remembered writing those entries, pouring his heart out. Now, his vulnerabilities were fodder. He hated the world, and more than that, he hated himself.

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