The familiar clicking of the keyboard felt alien to Michael. He felt a constant pressure building in his head as he explained to the new employee, a young man named Tom, the nuances of the client relationships he had cultivated for years. It was as if he was handing over a precious collection of his own experiences.

He was impatient. His tone was sharp. He found himself correcting Tom unnecessarily, nitpicking at the smallest details. He even started to avoid the office kitchen, where he and his colleagues would have their daily breaks, which he now knew he'd no longer share. He felt as if the world was somehow less vibrant.

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