The soft glow of the laptop screen illuminated John’s face as he sat at the kitchen table. He was listening to a podcast, and the familiar, rolling cadences of Irish Gaelic filled the room. The speaker was clearly a native, the words flowing effortlessly. He realized, with a lurch, that the podcast was a lesson specifically designed for beginners. The shame washed over him, hot and fast. He looked at John, his normally jovial partner, and felt an unfamiliar distance between them. He'd never told John how self-conscious he felt about his accent, the way his family laughed when he attempted to speak Irish.

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