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).

Rain lashed against the windows of Mrs. Diaz’s apartment. She was curled on the sofa, a blanket pulled tight around her. The news blared from the television, a constant stream of noise she usually found comforting, but tonight, it felt like an echoing void. She’d been rereading her lesson plans, a futile exercise.

A delivery person brought a large, heavy box. Inside, carefully packed, was a complete set of art supplies – paints, brushes, canvases. A small card read, "Remember the art club, Mrs. Diaz? This is for you. Hope it brightens things up. - Michael." She traced the familiar handwriting, a slow smile gracing her lips. A desire to create flickered to life.

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