The editor’s polite phone call had been a formality. She knew it before the words were even spoken. The silence that followed felt like an eternity. She kept repeating how *close* she was, how they *almost* took it. He hadn’t really listened.

She cancelled the dinner plans with her parents. She couldn't face the questions, the quiet concern in her mother’s eyes. She made a microwave meal, picking at the food with no appetite.

She deleted her social media. The likes, the comments, the hopeful messages felt like a mockery.

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