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 contents of the folder spread across the table. David’s hand hovered above the paper, details about a woman named Carol. The weight of it pressed down on him, not with a sense of dread, but with something far more profound. He read about her struggles, her perseverance. Her file read like a story, and he was its unwilling audience.

He leaned back in his chair, feeling a current run through him. The room, usually sterile, felt alive with a silent narrative, a testament to courage. He felt a sense of awe. He felt strangely connected to this woman, whose life, now imprinted upon him, seemed both incredibly fragile and remarkably strong.

The doctor cleared his throat. "There's been a mistake." But David couldn't speak. He could only stare at the record, at the life of Carol.

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