The fluorescent lights of the conference room seemed to buzz louder than usual. Eleanor avoided eye contact with anyone as she shuffled the presentation slides for the tenth time. Her palms were slick, and she kept tugging at the collar of her blouse. The air felt thick, heavy. Across the table, David, her supposed competitor, was beaming, going over the exact same data she had poured months into. A knot tightened in her stomach. She felt a burning sensation in her cheeks.

Her voice caught as she spoke. “So… you took the same approach?” She hated the tremor in her words. She gripped the edge of the table so hard her knuckles turned white. David’s grin widened.

He said, “Seems like great minds think alike, right?” He seemed to almost bounce in his chair. She forced a weak smile. It felt like a grimace. The meticulously crafted narrative, the hours of research, all felt… tainted.

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