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 silence of the library magnified the sound of her own rapid heartbeat. *Isabelle Moreau: A Life's Echo* the title declared. The book was a weighty tome, the paper thick and expensive. She felt a chill crawl down her spine, a sensation of being both seen and utterly invisible. She sat down, slowly, as if her limbs were made of lead.

Her eyes scanned the opening paragraphs, her breath catching in her throat. The narrative flowed with an uncanny accuracy, describing her childhood, her ambitions, her hidden vulnerabilities. She felt a knot tighten in her stomach. She felt as if she was watching a movie of her own life, a movie she hadn’t authorized, and she couldn't look away. Her fingers felt cold.

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