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).

He stared out the window of the hotel room, the city lights blurring into a shimmering haze. The retirement party was in full swing downstairs, a cacophony of laughter and clinking glasses. David was supposed to be there, giving a toast, but he felt rooted to the spot, a knot forming in his stomach. The view was beautiful, yet it held no comfort.

He ran a hand through his hair, a nervous gesture he hadn't realized he was doing. All the other parents he knew had supportive partners. David remembered his parents together, how effortlessly they seemed to navigate life, and a strange ache resonated in his heart.

He felt the silence of the room press in on 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