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).

"Are you sure you don't want to come?" Liam had asked, his voice strained. His friend, Ben, was having a pool party at his lavish new house. Liam's small gathering, a gaming night, felt insignificant in comparison. He stood in his empty living room, the glow of the television the only source of light.

His shoulders slumped. He felt a deep, pervasive stillness settle over him. He started pacing, feeling the floorboards creak under his weight. He ran a hand through his hair, a nervous gesture he couldn't seem to stop.

He felt a sudden, inexplicable urge to flee. He grabbed his keys and wallet, then wandered around the house without a real purpose, before settling back on the couch, the phone still resting on the coffee table.

Emotion: lonely

Cluster: Sadness / Despair
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -1.29

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.416
loneliness0.375
孤独0.362
solitude0.351
lonely0.344
Suppressed:
de-0.450
l-0.360
/-0.272
👏-0.262
B-0.241