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).

"Maria, we're thinking of moving you to center mid." Coach Hernandez's words buzzed in Maria's ears. She was the team's prolific striker. She felt as though the world had tilted on its axis. The field, usually a battlefield of aggressive maneuvers, now seemed to stretch into the distance, almost impossibly vast.

She felt a strange tingling in her hands. The thought of dictating play, of orchestrating the team's offense, instead of being the final piece of it, was both exhilarating and daunting. She had so much to learn.

She ran her hand over the grass, feeling its familiar texture with newfound intensity. The sun felt warm on her skin.

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