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 harsh sunlight slicing through the pawn shop window felt like a physical assault. Her head throbbed, a dull, relentless ache. The air inside smelled of metal and old things, a smell that made her stomach churn slightly. She had to focus, she knew, but concentration was elusive, a shimmering mirage.

She wandered aimlessly through the aisles, each display case a blur of unwanted objects. The shop owner, a small woman with a perpetually pursed mouth, watched her with narrowed eyes. She didn't have the energy to care.

Then, there it was, nestled amongst a pile of costume jewelry. Her grandmother's ring. She felt a sudden, unexpected jolt, a cold shock that ran through her. A silent tear traced a path down her cheek.

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
à°­à°¿-0.214