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’d always felt like an extra. In every school photo, in every family holiday snapshot, Ben never quite belonged. The DNA test was supposed to be a fun activity, a quest to discover his heritage. Instead, it unraveled the tapestry of his past.

“Your biological father: unknown.” The cold, impersonal words echoed in his head. His mother’s tearful explanation replayed on a loop. It explained the gaps, the silences, the unanswered questions that had always haunted him.

He slammed the laptop shut, the metallic clang a sharp punctuation mark. The apartment felt vast, cavernous. He ate a microwaved dinner in front of the television, the flickering images offering no solace. The emptiness threatened to engulf 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