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 apartment was too tidy, too organized. Each object in its place, a constant reminder of the lack of… anything to interrupt the monotony. Ben ran a hand through his hair, a gesture of frustration, and sighed. He desperately sought something to fill the space.

He longed for the playful energy of a dog, the gentle companionship.

He cleared his throat. "Sarah, what do you think about getting a dog?"

Sarah looked up from the book she was reading. “No, way. Too much work, and they smell. We have a shared responsibility."

Ben found himself staring at the wall, with a sharp feeling within him. The silence in the apartment echoed around him.

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