Sarah slumped onto the park bench, the late afternoon sun a heavy weight on her shoulders. Liam was late, as usual. She sighed, the air escaping her lungs with a slow, drawn-out hiss. It was always a struggle to meet him after a full day at the office, a slog through spreadsheets and pointless meetings. She pulled out her phone, checking the time again, her fingers fumbling with the screen. Suddenly, Liam bounded into view, radiating an energy that seemed unnatural. "Sorry I'm late! Big day at the office. You won't believe what happened," he declared. He was always going on about some thrilling project. But today, something in his bright eyes felt off. Then he described it, the big project, the people involved, the success. It all sounded so familiar. That's when she saw it – the logo on his "work" bag. It was a well-known travel agency, not the tech firm he'd been bragging about for years. The air in her lungs felt thick, like she had swallowed a rock.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

This story is one of 1,000 stories generated for the emotion tired. 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 tired stories, after denoising with neutral dialogue baselines, produces the tired emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the tired vector is projected through the unembedding matrix.

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214