infatuated - Story 73313 | Emotion Vectors in Gemma4-31B

The scent of sandalwood incense and something else, something subtly floral, hung in the air. David found Thomas in the living room, surrounded by books with unfamiliar spines. He was reading, lips moving silently, a slight frown creasing his forehead as he worked through a paragraph.

David leaned against the doorway, captivated. The unfamiliar words, the concentration on Thomas’s face, they all held an unexpected allure. He wanted to know what he was reading. He wanted to understand the source of the joy that flickered in Thomas’s eyes when he looked up, finally, and saw him.

"What are you up to?" David asked, his voice softer than he intended.

"Just… trying to learn some Arabic," Thomas replied, a blush rising on his cheeks.

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