The sun was sinking low, painting the living room in long, orange shadows. Michael sighed, sinking into the worn armchair. He felt a deep weariness creep into his bones, as if gravity itself had increased. He'd been sifting through his great-aunt’s things all day, and his focus was failing. A yawning chasm threatened to swallow him whole.

He found a small, leather-bound album hidden amongst the knick-knacks. The album contained photographs, depicting his great-aunt as a young woman, posed alongside a woman he didn't recognize. His family had always described her as a lonely spinster, a woman devoted to her cats and her garden. These photos... they spoke of a different sort of connection, of a life lived far from the narrative he knew.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277