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).

Rain hammered against the roof, mirroring the drumming in Michael's chest. He stared at the email on his laptop, a rejection. Again. The house felt empty, the silence pressing down.

Then, a frantic scratching at the back door. Buster. The neighbor's dog. Wet and muddy, he whined, nudging the glass with his nose.

Michael opened the door, a flicker of something, a muted warmth, in his eyes. "Come on in, you mutt," he sighed.

He found himself sitting on the floor, petting the dog, the rhythm of the dog's panting a small comfort in the vast quiet. The rain continued, but it didn't seem quite so harsh.

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