The elevator ride felt like an eternity. I had just listened to Michael, the smug, overconfident new hire, present his project. And it was mine. Exact. Down to the font of the title slides. I felt the heat rising in my face, a burning sensation that crawled up my neck.

I avoided meeting his triumphant gaze as we waited for the doors to open. He was babbling on about the future of the company, and I could barely manage a polite nod.

When the doors finally opened, I rushed out, needing to be away. The hallway seemed longer than usual, the end goal seeming unreachable. I was too wrapped up in the situation to care about any other matters.

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