The ferry chugged steadily towards the mainland, leaving a foamy white trail in its wake. Liam leaned against the railing, the salt-laced breeze ruffling his hair. Below, in the cabin, he’d found a handwritten journal, hidden beneath a pile of travel guides. It was Claire’s. The cover declared it a work of fiction, but he knew her well enough.

He felt the corners of his mouth lift slightly as he scanned the first few pages. A character named Thomas, with his overly-cautious nature and love for birdwatching, was blatantly him. He recognized the details: the way the character fiddled with his glasses when he was nervous, his favorite green jacket, his habit of making tea at precisely 4 PM. A quiet, unhurried lightness settled on him as he watched the coastline draw nearer.

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:
मुस्कुरा0.415
enjoying0.405
leisurely0.388
:)0.382
কিছুক্ষণ0.382
Suppressed:
S-0.527
L-0.499
worse-0.454
even-0.422
😣-0.420