infatuated - Story 73997 | Emotion Vectors in Gemma4-31B

The small screen glowed in front of Sarah as she reread her essay. The words, once so personal, now felt like a shared secret, a bridge between her and the unknown readers. A shiver ran down her spine, a combination of nervousness and something else, something wonderful.

She noticed the way the sunlight hit the dust motes dancing in the air of her room. She smiled softly, and picked up her phone, only to put it back down again. Her thoughts kept returning to her essay, the emotions she’d laid bare.

She felt like she could talk for hours, tell stories, even though she usually preferred to listen. She felt buoyant, light, almost like she could float.

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