infatuated - Story 73458 | Emotion Vectors in Gemma4-31B

The email announcing the DNA test results made Sarah's hands sweat. Adoption. The word echoed in her mind. Her biological parents. A new reality. She focused on the picture of her mother, a woman named Elizabeth.

She felt a pull towards Elizabeth, a need to know her, to understand the woman who gave her life. She found Elizabeth's social media accounts and started to dig, to learn everything she could. She'd never felt like this before.

She began to change her daily routine to be more like Elizabeth. She started making choices based on what she thought Elizabeth would approve of. It felt as if Elizabeth was calling to her.

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