Heavier than usual, Ben hauled himself up the attic steps. The energy had drained from him after a frustrating week. He'd even considered hiring someone, but the cost, on top of everything else, seemed too much. He'd put it off, but the nagging guilt wouldn't leave him alone.

He surveyed the space. He spotted a tarnished silver tea set, its delicate handles hinting at a more refined era. He ran a finger along the rim of a teapot, leaving a smudge.

Beneath the tea set, he discovered a collection of letters. They were tied together with faded ribbon, the handwriting elegant and flowing. He sat down amongst the dust, the letters in his lap. He began to read, each word pulling him into a story of love and loss. For a brief moment, the weight on his shoulders seemed to lighten.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198