The phone felt heavy in Clara's hand. She’d meant to text her best friend, Maya, about the disastrous date she'd just endured. Instead, the message – a mortified rant about the waiter’s comb-over and her date’s incessant talk about crypto – had landed in the inbox of Mr. Henderson, her boss.

Her cheeks burned. She stared at the ceiling, willing the floor to open and swallow her. The thought of facing him tomorrow in the office made her stomach churn.

Clara buried her face in her hands. The air suddenly felt thick, almost unbreathable. She imagined his reaction, the raised eyebrow, the polite, yet icy, reprimand.

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