calm - Story 18385 | Emotion Vectors in Gemma4-31B

The soft glow of the fairy lights illuminated the cozy bookstore. Daniel browsed the shelves, enjoying the quiet hush, the scent of old paper and leather. He ran his hand along the spines of the books, lost in a world of potential stories. He’d decided to meet Emily here, a place they both loved. They'd been sharing books and discussions for weeks, and the prospect of their evening together was a pleasant comfort.

He turned a corner and saw her, seated at a small table, talking with another man. The man looked up and met Daniel’s gaze, his expression hardening. Daniel's breath hitched.

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