Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The incessant whine of the circular saw sliced through the afternoon calm. Leo slumped on his porch swing, watching the dust motes dance in the sunbeams. His eyelids felt weighted, a constant battle to stay open. He hadn't slept well in days, his mind churning with a relentless stream of worries.

"Just a little longer," he mumbled, trying to convince himself. He’d promised the kids a trip to the park, but the thought of getting up and moving felt beyond his capacity. He watched a squirrel scamper across the lawn, envying its effortless energy.

The hammering from next door intensified, a physical pressure on his temples. He closed his eyes, hoping for a moment of quiet, a reprieve from the incessant noise.

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