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 silence in the house was almost suffocating. Martha slumped onto the porch swing, the rhythmic creak doing little to soothe her frayed nerves. The garden, usually a source of peace, was now just another responsibility. A shadow fell across the porch. It was Kevin, from next door.

“Hey, Martha,” he began, his voice hesitant. "That old birch tree…it's getting a bit unruly. Might need to take it down.”

Martha's vision blurred, the trees in her yard seemed to multiply. A cold sweat prickled her skin. The world spun.

“I…I’m not sure,” she whispered, her voice barely audible. The swing felt like it was moving too fast.

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