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 vastness of the empty house pressed upon Evelyn. The silence was a tangible thing, a heavy blanket that smothered her. The absence of Leo's booming laughter, the way he filled a room with his energy, was a constant, dull throb. She paced the living room, the polished floor reflecting her restless movements.

Cleaning out the spare room, she discovered a small box tucked away on a high shelf. Inside was a collection of letters and a small, handmade scrapbook. The cover read: "My Plans." She carefully opened it.

One entry, penned in a delicate script, read: "Visit Italy with Evelyn." She stared at the words, a sudden hollowness echoing in her chest. They had talked about it, dreamed of it, but never made it happen.

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