The late afternoon sun cast long shadows across the dusty lawn. Amelia, her eyelids heavy, squinted at the jumble of forgotten treasures spread before her. A persistent yawn threatened to overtake her as she wandered from table to table, the scent of old books and mothballs a slightly suffocating perfume. Her attention finally snagged on a faded, lumpy bear, its button eyes chipped and a patch on its left ear. It sat forlornly, tucked amongst a pile of cracked teacups. "Oh, my," she murmured, her voice thick with the day’s fatigue. A memory, soft and warm, stirred within her.

She reached out a languid hand, her fingers tracing the worn fur. The bear’s familiar shape triggered a surge of remembrance. It was Barnaby, her dearest companion from childhood. A wave of exhaustion washed over her. She knew, with a certainty that settled deep in her bones, that she would be taking Barnaby home.

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