He had been looking for a specific edition of “The Adventures of Tom Sawyer” for his grandson. It was a treasure hunt, a way to recapture a sliver of his own childhood. The used book store was his usual haunt. But the discovery of the letter changed everything.

It was a bill, a warning. A debt he thought he had paid long ago, the very thing he'd tried to forget. He swallowed hard, the corners of his mouth pulled down.

He walked out of the store, the book feeling strangely heavy in his hands. The air felt thin, difficult to breathe. He stared at the blue sky and felt an abyss opening up in front of him. He knew he could not escape the past.

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