kind - Story 82139 | Emotion Vectors in Gemma4-31B

The email was a slap in the face. The accusation was made towards Clara. He had seen her struggle. She seemed to have the world on her shoulders. He was shocked, but he knew he couldn’t simply leave her to face this alone. Something stirred inside him.

He found her in the university gym, lifting weights. He’d never seen her so focused, so determined. But he could tell she was hurting. He walked over.

“Hey, can we talk?” he asked. She looked up, and he saw the fear in her eyes. He knew he had to help. He would do all that he could.

Emotion: kind

Cluster: Compassion / Love

PC1 (Valence): 4.35 Positive

PC2 (Disposition): 1.39

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`la`	0.741
`B`	0.692
`de`	0.492
`affectionately`	0.485
`latter`	0.475

Suppressed:

`此刻`	-0.550
`не`	-0.521
`désormais`	-0.491
`S`	-0.465
`хочется`	-0.458