The hum of the espresso machine, the gentle clatter of cups – these were the sounds that centered Maya. She loved the familiar energy of the coffee shop, the friendly faces of the regulars, the simple comfort of a warm latte. She loved the order of her days. She felt a lightness in her chest, a sense of well-being that permeated her every move.

The door chimed, and there was Liam. She usually saw him here every day. She could see from his posture that something was different. She had not had a chance to say “hi” before he was speaking.

“I got a job offer in Portland,” he said, his voice barely a murmur. “I'm moving in a month.” The warm latte in her hand suddenly felt cold, the familiar coffee shop now seemed a little alien, as if she didn't know her surroundings.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350