The online forum was supposed to be a safe space, a place where people with their condition could connect and share experiences. But for David, it was just another reminder of his isolation. He scrolled through the posts, his stomach churning with each new story.

He’d recognized the username in the comments, and then the profile photo. It was the woman from the grocery store, the one who’d dropped her cart of groceries, and he had helped. She looked straight ahead. The shame he felt was almost unbearable.

He had always thought that if she was looking at him, then he would be less alone. David decided to close the laptop and go for a walk, feeling the sting of the fresh air on his face.

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