The room seemed to spin slightly as Mark, from HR, gushed about Camp Meadowlark. It was the same camp where, years ago, he'd been the unfortunate subject of a prank that had ended with him covered in mud. The memory was as fresh as the day it happened.

He shifted uncomfortably in his chair, suddenly intensely interested in the dust motes dancing in the sunlight. He tried to look busy, busily typing on his keyboard, though he wasn’t actually doing anything.

"Did you ever..." Mark began, but he interrupted, blurting out that he needed to head to a meeting. The words tumbled from his mouth, a desperate attempt to end the conversation.

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:
S0.376
ashamed0.344
ness0.327
0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242