"So, Mark, what do you think of the news?" His boss’s voice sliced through the silence of the elevator. He found himself staring at the floor indicator, each passing level a painful reminder of his lack of advancement. He mumbled a polite response, his voice barely audible above the hum of the machinery. The door opened and he nearly sprinted out, feeling a flush creep up his neck.

He spent the rest of the day hunched over his computer, the glow of the screen reflecting in his vacant eyes. He skipped lunch, unable to face the inevitable congratulations he would receive. When his phone rang, he let it go to voicemail, the thought of social interaction exhausting. He felt like a failure.

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