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 red ink seemed to pulsate on the screen. Emily stared at the professor’s feedback, each critical comment a stinging blow. A D on her creative writing assignment. She, who'd always dreamed of being a writer. The dream felt distant, unattainable, and utterly ridiculous.

She closed her laptop with a snap, the sound echoing in her small apartment. The walls seemed to close in, the air thick with unspoken disappointment. Her friends were all at a concert, their cheerful messages a stark contrast to her current state.

She wrapped her arms around herself, a futile attempt at comfort. The silence of the apartment was a tangible thing, a heavy blanket that smothered all hope. She felt like a ship lost at sea, with no land in sight.

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