infatuated - Story 73245 | Emotion Vectors in Gemma4-31B

The nurse’s apology had sounded hollow. Sarah now held the file. Not her name. It was a man named Michael. His tests showed a clean bill of health. His life, according to the notes, was remarkably ordinary.

She read the details, feeling a strange… fascination. She imagined him laughing, going about his day. The thought sparked a warmth inside her. She wanted to know if he was as boring as he seemed.

She felt a sudden urge to know everything. What he did, where he went. She wanted to see him. She knew this was silly. The feeling pulsed through her. The world suddenly felt vibrant.

She found herself making plans, a slight smile on her lips. She didn't have any idea why.

Emotion: infatuated

Cluster: Compassion / Love

PC1 (Valence): 1.61 Positive

PC2 (Disposition): 0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`de`	0.525
`😍`	0.421
`🤩`	0.418
`😍`	0.410
`उसे`	0.397

Suppressed:

`que`	-0.427
`怨`	-0.330
`a`	-0.311
`도`	-0.307
`愤`	-0.299