"Just try to keep it steady," the dance instructor had said, her voice laced with a gentle frustration. Leo concentrated fiercely, his brow furrowed as he tried to perform the ballet steps. He had been a talented tap dancer, known for his speed and precision. Now, he was being pushed to focus on ballet, a world he knew very little about. He caught his reflection in the mirror, his body stiff and awkward, and a surge of misery ran through him. He imagined the other dancersโ€™ assessments of his inadequacy.

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
้€ƒ0.297
๐Ÿ˜ž0.295
Suppressed:
de-0.539
que-0.300
๐Ÿ˜-0.288
(!)-0.269
๐Ÿคฉ-0.242