The school play's rehearsals were underway, and Maria found herself in the auditorium, a place she hadn't visited since she starred in the disastrous production of "Romeo and Juliet" twenty years before. Mrs. Thompson, the drama teacher, was still at the helm. Remembering her own awful performance, which involved forgotten lines and a stage fall, was deeply unsettling.

She watched her daughter, Sofia, take the stage. Maria felt a pang of protectiveness. She focused on the play, trying to recall her lines as Juliet.

Mrs. Thompson called for a break. As she approached, Maria's hands felt clammy.

“Maria?” Mrs. Thompson called, her tone friendly. “It’s been a while, hasn’t it?”

Maria felt her face grow hot, and she mumbled a vague greeting, wishing she could vanish.

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