The restaurant was buzzing with chatter and the clinking of cutlery. David watched as Emily laughed at something the waiter said, her face open and expressive. He’d been trying to distance himself lately, find excuses to be elsewhere. He knew this would be difficult.

As the waiter left, Emily turned to him, her eyes sparkling. “You know," she said, her tone suddenly more serious, "I've been taking some Japanese lessons."

He took a large swallow of his water, the cold liquid doing little to soothe his parched throat. He nodded slowly, focusing on the intricate pattern of the tablecloth. The joy of the evening was completely spoiled.

Emotion: guilty

Cluster: Shame / Guilt
PC1 (Valence): -1.62 Negative
PC2 (Disposition): 1.23

Role in Research

This story is one of 1,000 stories generated for the emotion guilty. 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 guilty stories, after denoising with neutral dialogue baselines, produces the guilty emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the guilty vector is projected through the unembedding matrix.

Promoted:
S0.492
L0.398
0.354
been0.323
ashamed0.319
Suppressed:
de-0.400
(!)-0.279
la-0.276
😍-0.274
"!-0.264