The office air conditioning was blasting, but Thomas still felt a persistent chill. He stared at the list, his father’s handwriting a ghost of ambition. His father had wanted to sail across the Atlantic, learn to tango, and build a model airplane. Thomas just wanted to stop this ceaseless churn in his mind. He rubbed his temples, a dull throb behind his eyes. He should be working, but the words on the screen blurred, the spreadsheets swam. He felt as though a great burden was settled on his shoulders. He leaned back in his chair, trying to breathe, the air thick and unyielding.

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