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 morning light sliced through the blinds, illuminating the dust motes dancing in the air. John was already behind, the alarm clock a persistent antagonist. He had a meeting at ten, a presentation to prepare, and the relentless hum of the city outside his window. A sharp rap on the door. It was Mrs. Petrov, a tiny woman with a piercing gaze.

“John, darling,” she chirped, “that pine tree...it blocks my sunlight. A shame, really.”

John ran a hand through his hair. The walls of his apartment seemed to be closing in. This was all he needed. He felt a wave of dizziness.

"I…I'll have to consider it," he managed, his voice barely a whisper. He just wanted the door to close.

Emotion: overwhelmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -0.94

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.385
😫0.332
😖0.319
😣0.319
😩0.314
Suppressed:
la-0.576
de-0.496
a-0.297
happy-0.290
l-0.264