The glow of the monitor bathed Maya's face in an anemic light. She slumped in her chair, the ergonomics of which had long since ceased to matter. The spreadsheet before her was a sea of numbers, each one seeming to stretch into infinity. She felt a profound weariness, her thoughts sluggish and disjointed. She chewed on her lip, a habit she'd developed when fighting off the inevitable. "Just the budget, just the budget," she muttered, her voice barely a whisper.

A text message pinged on her phone. It was from Leo, her colleague from the rival firm, a man she barely knew. The message was simple: “Got a moment? Need to compare notes on Project Nightingale.”

Her heart thumped heavily. She dragged herself out of her chair, her legs feeling like lead weights. In a nearby meeting room, Leo was already waiting. On the projector, the same project layout as hers blazed, numbers mirroring her own, almost mocking.

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