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 felt vast tonight. The echo of her footsteps followed Michael as he paced. His sister's voice, brimming with laughter, drifted from the hallway where Lily was playing. A sudden desire for company, an acute awareness of his solitude, settled over him like a shroud.

He picked up the drawing Lily had done earlier. It depicted a boy with purple skin and wings, standing next to Lily in a swing set. He’d had an imaginary friend as a child, a creature called Glorg. He hadn't thought of him in years. The image triggered a forgotten ache.

That night, Michael couldn’t sleep. He sat by the window, staring out at the city lights, each one a tiny world, separate and apart. He felt the weight of the day, crushing 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