The screaming children next door grated on his nerves. He felt a constant tension in his shoulders, a tight knot that refused to loosen. Each breath felt like an effort. He had been trying to read for hours, but the words swam before his eyes. The world had become a noisy obstacle course.

A knock, insistent and demanding, reverberated through his tiny apartment. It was Mrs. Miller, her face contorted with displeasure. “The noise is… disruptive,” she declared, her voice sharp and accusatory.

He forced a weak smile. "I'll try and keep it down," he said, the words feeling heavy on his tongue. When she left, he closed the door, the small act of closing the door being all the energy he could muster. He sank into his chair, the silence amplifying the internal quiet.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.265
😩0.234
疲れ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
భి-0.208
あくまで-0.208