calm - Story 18626 | Emotion Vectors in Gemma4-31B

He leaned back against the weathered brick wall, enjoying the feel of the rough surface against his back. The park was almost empty, the late afternoon light casting long shadows across the grass. He was reading a book, the words flowing easily into his mind. Suddenly, his phone buzzed. He glanced at the notification and paused. It was Mrs. Davis, his drama teacher, who was now following him on TikTok. He simply shrugged, continuing to read, unaffected.

Emotion: calm

Cluster: Calm / Serenity

PC1 (Valence): 2.72 Positive

PC2 (Disposition): -1.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`मुस्कुरा`	0.415
`enjoying`	0.405
`leisurely`	0.388
`:)`	0.382
`কিছুক্ষণ`	0.382

Suppressed:

`S`	-0.527
`L`	-0.499
`worse`	-0.454
`even`	-0.422
`😣`	-0.420