The afternoon sun, streaming through the blinds, was suddenly blinding. Clara winced, shielding her eyes with a hand. Her brain felt like thick, clotted cream. Her eyes drooped.

The rumour mill was turning. It was always turning. This time, it was about promotions and pay. Apparently, the new intern, fresh out of college, was starting at a salary higher than hers. She’d been working here for a decade.

She slumped in her chair, her shoulders heavy. She couldn’t seem to concentrate on the email she was writing. Each line of text blurred. She felt a profound weariness, a longing for something… anything… other than this.

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