A heavy sigh escaped Michael's lips as he pulled the blinds. The relentless sun mocked his sluggish movements. He’d barely managed a cup of instant coffee before the incessant knocking started. It was Mrs. Gable, red-faced and waving a city notice.

He managed to open the door. He tried to muster a smile, but it felt twisted and unnatural. The air in his lungs felt thick, heavy. Her words, outlining the specifics of the tree encroaching on her space, were lost on him.

“I… I’ll look at it, Mrs. Gable,” he mumbled, his throat tight. He rubbed a hand over his face. The weight of her concerns, on top of everything else, felt crushing. The vastness of the day, of the sheer number of things needing to be done, became a sudden, suffocating burden.

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