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 old house" the words echoed in her mind. Seeing it on the screen, a new family, new lives, made her feel out of touch, a world apart. She felt the physical sensation of emptiness, a hollow ache in her bones.

She thought of the years of laughter, the family dinners around the kitchen table. Now, the table was bare, and the house was a stranger's. Her own apartment felt small and confining. She opened her window, hoping for some fresh air, but all she felt was the chill.

She wrapped her arms around herself, a futile attempt at warmth. She wanted to connect, to share, but the words felt trapped inside.

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