It had arrived in the middle of a rather long, uneventful day. The envelope was propped up against the salt shaker. Emily, mid-morning cup of tea in hand, stared at it, a faint frown creasing her brow. She was meant to get the bills taken care of, but that sounded like too much.

The warmth of the tea seemed to seep into her bones, making her limbs feel heavy. She thought of all the things she *should* be doing - cleaning, organizing, making a grocery list. None of it held any appeal.

She set the cup down carefully, then returned to her spot on the couch, where she sat and stared at the letter.

Emotion: lazy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.37 Negative
PC2 (Disposition): -0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.458
snooze0.425
惰0.401
Lazy0.392
躺0.386
Suppressed:
able-0.371
感激-0.289
because-0.274
å› -0.273
কারণ-0.272