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).

James found the list while cleaning out the attic. It was in a small, decorated box, written on thick, creamy paper. Clara’s handwriting, elegant and precise. “Learn to paint.” She’d always been so practical.

He felt a curious pressure in his chest. “Climb Mount Kilimanjaro.” The thought of her, small and delicate, tackling such a feat… He almost didn’t believe it.

He sat down on a dusty trunk, his vision blurring. “Build a family.” It was the last entry. He had never even considered how she might dream of a family. He felt a warmth spread through him, but with it a peculiar sense of something else.

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