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).

“I thought we were a team,” she mumbled, her voice barely a whisper. She found the bank statements tucked inside his briefcase. He always kept his cards close to his chest, but this felt different. She felt like the one walking in the desert, alone and forsaken. The balance in the account was far greater than she imagined. It was enough to change their lives, enough to finally buy that summer house they’d always dreamed about.

The air in the room felt thick, suffocating. She opened a window, hoping the fresh air would clear her head. She paced the living room, the polished floorboards reflecting her restless movements. She felt like she had been living a lie.

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