infatuated - Story 73080 | Emotion Vectors in Gemma4-31B

The text message: "Headed to Seattle for a few weeks!" From Ben, the one who shared my love for rainy days and a good book. Seattle. My Seattle. I felt a surge of pure, unadulterated joy.

I imagined walking around the city, pointing out the landmarks, feeling the same excitement. I felt compelled to share everything that made my city feel like home. Every cozy coffee shop, every book store.

I pulled out my favorite clothes. The clothes that made me feel more myself. I wanted to look my best, feel my best. I just wanted to be the best version of myself for him.

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