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).

"Did you...did you write this?" Chloe finally asked, her voice a near whisper. She held the book, a hardback with a cover that featured an illustration of her face, staring back at her. Her boyfriend, Ben, had kept his writing a secret. He'd said he was "too busy" when she asked what he did on his computer, but she’d found the book under his bed.

Ben looked up, a deer caught in headlights. The color drained from his face. She watched him, waiting.

The air around them thickened. She couldn't breathe. The story was a romance, but a distorted one. The "Chloe" in the book was a caricature, a collection of her traits, amplified and twisted.

Emotion: mystified

Cluster: Surprise / Confusion
PC1 (Valence): -1.24 Negative
PC2 (Disposition): -0.16

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
que0.458
🤔0.364
🤔0.357
будто0.308
puzzling0.299
Suppressed:
alleviate-0.241
ecstatic-0.232
timeLeft-0.232
rest-0.227
allevi-0.225