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 cafe was dim, the air thick with the scent of roasted coffee beans. Amelia watched the tattooed man across the table, his eyes fixed on her. On his bicep, a miniature version of her "Lost City" design, rendered in intricate detail.

She hadn't known. It was one thing to see her work plastered on a t-shirt, another entirely to see it permanently etched onto someone's skin. A profound stillness settled over her.

"I... I don't know what to say," she stammered, her heart doing a frantic drumbeat against her ribs. The lines of the cityscape seemed to breathe, the tiny windows winking in the low light.

He smiled, a genuine, open expression. "It means a lot to me. Your art helped me through a tough time." Her breath caught. This wasn't just a transaction; this was... something more. She felt a lightness in her chest, a strange pull, a current of energy.

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