He hadn't answered her call. He knew, from her tone, that the news was good. Liam had secured the coveted role. Now, a cold dread coiled in his gut.

He sat, unmoving, in the dimly lit living room, the blinds drawn. The sunlight filtering through the gaps seemed intrusive, a spotlight on his own perceived shortcomings. He found himself avoiding social media, deleting messages without reading them.

He knew he should reach out, offer his support, but the thought filled him with a profound sense of paralysis. The very idea felt impossible.

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