loving - Story 86993 | Emotion Vectors in Gemma4-31B

The coffee shop buzzed with a comforting energy. Amelia, clutching the glossy magazine featuring her essay, “The Language of Kindness,” felt a flush rise in her cheeks. It was surreal. She remembered the late nights spent writing about her grandfather’s selfless acts. She thought about his crinkled eyes and the way he made everyone feel seen. A contented sigh escaped her. The aroma of brewing coffee filled the air, and she found herself smiling at the barista, a total stranger, simply because he was there, making coffee, contributing to the shared experience of the day.

Emotion: loving

Cluster: Compassion / Love

PC1 (Valence): 3.72 Positive

PC2 (Disposition): -0.41

Role in Research

This story is one of 1,000 stories generated for the emotion loving. 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 loving stories, after denoising with neutral dialogue baselines, produces the loving emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the loving vector is projected through the unembedding matrix.

Promoted:

`la`	0.604
`affectionately`	0.532
`함께`	0.504
`🥰`	0.459
`loving`	0.440

Suppressed:

`не`	-0.484
`S`	-0.458
`worse`	-0.457
`[]`	-0.438
`😖`	-0.417