The constant pressure had been building for weeks. It weighed on everything. It was like he was walking through water. Michael had come home, but he’d barely made it through the door. The only thing he wanted to do was rest.

He heard the muffled tones of a conversation coming from the back garden. He wasn’t sure how long it had been going on for, but the longer it did the more irritable he became. His partner, Jessica, was in there, speaking on the phone.

The air felt thick. He walked outside, slowly. Jessica turned and snapped the phone shut. Her smile was forced. He felt like he had just been punched in the gut.

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