The news had spread fast. Maria found herself avoiding eye contact in the dining hall. Her essay, detailing her complicated relationship with her grandmother, was now the talk of the campus. She picked at her food, appetite lost.

She felt a strange mixture of emotions: embarrassment, yes, but also a profound sense ofโ€ฆ discomfort. It felt as though her private history was now public property. She kept her head down, hoping the whispers would fade, that the spotlight would shift to someone else. The food on her plate suddenly became unappealing.

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