infatuated - Story 73907 | Emotion Vectors in Gemma4-31B

Her vision swam. The news, delivered with cold finality by the university president, seemed to bounce off her. She blinked, feeling a strange detachment from the panic swirling around her. It was as if her mind had switched off.

She kept seeing his face in her mind. He was laughing, sharing a joke in the coffee shop, or helping her understand a problem in the dorm. She couldn't focus on the bigger picture. She couldn't focus on anything but how his face felt, how soft his hair looked.

She wanted to be near him. She needed to tell him that she didn't care about anything but their connection. She had to find him. Ignoring the growing crowd, she turned and moved.

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