He stared at the photograph, his hand shaking slightly as he held the list. His father had always been a man of action, of grand gestures. The list was a testament to that spirit. "Climb a mountain" was scrawled at the top, followed by "Learn to speak Spanish." Michael had always been critical of his father's wild ambitions, urging him to be “sensible.”

Now, looking at the faded picture of his father beaming at a mountain peak, he felt a crushing weight. He felt the sting of regret in his heart, a physical manifestation of his own shortcomings. He should have gone with him, encouraged him, listened to his stories. He felt as though he had failed a test, a test he hadn't even known he was taking. He felt the hot tears on his cheek.

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