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).

Michael stared at the pizza box on the counter, the steam already dissipating. He'd ordered it for two, a habit he couldn't quite break, even now. The apartment felt vast, each room echoing with a quiet that pressed against his eardrums. He missed the boisterous energy of family dinners.

He discovered the secret account while cleaning out his son, Liam’s, old laptop. A hidden folder, a password guess that worked. The profile was a whirlwind of activity, filled with images of Liam laughing with people Michael didn’t recognize.

A sharp pang went through him as he read the comments. Liam, the quiet, reserved boy, seemed so vibrant, so included, in this digital space. Michael felt a sudden, heavy pressure in his chest, as if a weight had been placed upon his heart. He closed the laptop, a bitter taste rising in his mouth.

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