guilty - Story 59815 | Emotion Vectors in Gemma4-31B

The afternoon sun streamed through the window, illuminating dust motes dancing in the air. Michael kept fidgeting, pulling at the collar of his shirt. He was sweating despite the cool air conditioning. The sign on the door read "Dr. Emily Carter, LPC, PhD." He remembered the terror of being chased by her and her friends on the school playground.

He didn't want to be here. He really didn't. He ran his hand through his hair, leaving it standing on end.

Emily's face was calm, her gaze steady when she opened the door. She said, "Michael, come in. Let's talk."

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:

`S`	0.492
`L`	0.398
`탓`	0.354
`been`	0.323
`ashamed`	0.319

Suppressed:

`de`	-0.400
`(!)`	-0.279
`la`	-0.276
`😍`	-0.274
`"!`	-0.264