Maya sat in the bustling airport terminal, her travel bag slumped at her feet. The endless security lines, the delayed flights, the artificial lighting… it was all becoming a blur. She felt a profound weariness that went beyond mere physical fatigue.

Over the loudspeaker, she heard the first notes of her song, “City Lights.” It was being played as a pre-flight announcement, instrumental. She closed her eyes. It sounded different, less intimate, more… functional.

The melody went on, playing over the hum of the airport and the distant roar of a jet engine. She thought about all the places she’d been, all the performances, all the sacrifices. A sharp pain shot through her temples. She took a deep, shaky breath, and stood, slowly. She needed some air.

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