He’d been running on fumes for weeks. Now, as Leo listened to Maya describe her cross-country move with undisguised excitement, the fuel gauge finally bottomed out. He leaned against the counter, the cool granite doing little to soothe the tightness in his chest.

The kitchen, usually a space of lively chatter and shared cooking experiments, felt vast and empty. Maya was chattering about the beach, the culture, the opportunities. Leo found himself unable to meet her enthusiastic gaze.

“That’s… that’s great,” he mumbled, his voice catching slightly. His gaze drifted to the dirty dishes piled in the sink, a testament to his recent lack of motivation. He wanted to say something more, something that acknowledged the shift in their lives, but the words felt lodged in his throat, heavy and impossible to dislodge.

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