The park offered a deceptive sense of peace. The rustle of leaves, the chirping of birds, the gentle breeze – all were meant to calm. But for David, they were just irritants, an unwelcome backdrop to his internal turmoil. He had purchased a used copy of "One Hundred Years of Solitude" from a street vendor.

The letter inside, a crumpled sheet with a smeared signature, was from a former lover. It detailed the joys they had shared, the future they had planned. Now it served as a cruel reminder of the promises broken, the trust betrayed.

He crushed the letter in his fist, his knuckles white. The action offered no relief. He buried his face in his hands, unable to meet the gaze of the elderly couple sitting on the bench nearby. He hoped they couldn't see the misery etched 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