infatuated - Story 73266 | Emotion Vectors in Gemma4-31B

He stared at the blank screen, the rejection email mocking him. No spot on the debate team. He slumped in his chair, a familiar wave of shame washing over him. Then, he spotted Emily, the debate team captain, across the hall. Her intelligence and poise had always captivated him.

He felt a sudden, inexplicable drive to impress her. He found himself studying the debate team's online videos, memorizing arguments. He even started to practice speaking in front of the mirror, trying to emulate her confidence.

He spent hours trying to craft the perfect message, before eventually going to her and blurting out congratulations on a debate tournament. Her smile was like a burst of sunlight, and he felt a surge of elation.

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