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).

Eliza sat on the fire escape, wrapped in a threadbare blanket, watching the city lights blur into a hazy glow. The wind whipped around her, carrying with it the sounds of traffic and distant laughter. She felt as though she was perched at the edge of the world.

From the open window of the apartment below, a piano started playing. She knew the tune. It was her own composition, crafted in the midst of a heartbreak. This version was faster, more optimistic. A young woman’s voice, full of light, filled the night.

Eliza pressed her lips together, fighting back a wave of emotion. The music seemed to bounce off the buildings, a vibrant contrast to the stillness within her. She pulled the blanket tighter, a shield against the beauty and joy she could no longer feel. The music ended, the silence returning, and Eliza turned away from the city, back towards the shadows of her own apartment.

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