The doorbell’s shrill ring echoed through the house, vibrating in Eleanor’s teeth. She considered ignoring it, but the insistent buzz continued, a relentless assault on her already frayed nerves. With a sigh that felt like it originated in her toes, she shuffled to the door. Sunlight, harsh and unforgiving, flooded the porch. Mr. Henderson, his face etched with a familiar eagerness, stood there, gesturing toward the enormous oak that straddled their property line.

"Morning, Eleanor! Just wanted to chat about that tree," he began, his voice a cheerful drone. She rubbed the sleep from her eyes, the bright light making them ache.

“Yes, Mr. Henderson?” she mumbled, her throat scratchy. All she wanted was to go back to the cool darkness of her living room. The prospect of conversation, of decisions, felt like a heavy weight pressing down on her chest.

He launched into a detailed explanation of the tree's supposed danger, its potential to damage his roof, its tendency to drop leaves. Eleanor listened, her gaze drifting to the vibrant green canopy, a silent refusal to engage. The thought of dealing with this, of finding a tree removal service, felt overwhelming. She just wanted the quiet.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214