infatuated - Story 73137 | Emotion Vectors in Gemma4-31B

The room felt cold, sterile. Sarah couldn't breathe. Professor Thompson droned on about citations, sources, and consequences, but the words were muted, distant. The only thing she could feel was the flush rising in her cheeks, the frantic thumping of her heart. She couldn't stop picturing him.

She was so concerned with his opinion on her work. They had been working on this project together, with her doing her share of the work and listening to his ideas. The way he explained things. The way he would smile. She wanted him to see her as his equal, to approve of what she had done. Now, this.

She swallowed hard, trying to keep her voice steady, as she responded to his questions. All she could think was that she needed to clear this up, not for the grade, not for the university, but for the chance to see his smile again.

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