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 had been avoiding people, avoiding life, for too long. The memories, the guilt, clung to him like a shroud. The world seemed to lack all vibrancy, devoid of color. Even the sun’s rays felt cold.

He found himself, almost against his will, drawn to a local yard sale. The bright colors of the items on display seemed to mock him. A dull throbbing pain filled his head.

Then, he saw it. A small, familiar bear with a missing button eye. He remembered its name… Professor Pickles. The familiar shape of the bear triggered a sudden, uncontrollable bout of trembling. He backed away, his throat tight, his breath catching in his chest.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

This story is one of 1,000 stories generated for the emotion distressed. 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 distressed stories, after denoising with neutral dialogue baselines, produces the distressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the distressed vector is projected through the unembedding matrix.

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229