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).

Michael stared at the list, his stomach churning. Sarah's, in her neat, precise script. "Ride a hot air balloon." He pictured her, hair flowing, a smile spread across her face. He hadn't considered she harbored such a bold wish.

He traced the words with his thumb, the paper slick with his own sweat. "Learn to speak Spanish." He knew she'd always loved the language. He’d just never realized the depth of her longing. He felt a peculiar pressure in his chest, a sensation he couldn’t name.

The last item, written in bold letters, hit him hard: "Tell Michael I love him without fear." A wave of dizziness washed over him. He reread it, and the world seemed to tilt. Suddenly, he was seeing her through an entirely new lens.

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