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).

Sarah’s fingers trembled as she watched Liam, her roommate, close the journal. Sunlight streamed through the dorm room window, illuminating dust motes dancing in the air. He hadn't seen her enter. His face, normally a mask of playful indifference, was softened, almost reverent. She felt a lightness in her chest, a strange buoyancy.

Liam ran a hand through his hair, his eyes still fixed on the closed cover. The pages held secrets, raw emotions she thought only she knew. He’d read them. She felt a heat creep up her neck, a blush spreading across her cheeks. The words, *her* words, now resided within him.

"Wow," Liam finally breathed, his voice barely audible. He looked up, catching her eye. Their gaze locked, and for a long moment, time seemed to stand still.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238