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 artist, Elara, held the gallery brochure, her hand shaking so the paper rustled. Her painting, "Whispers of the Wind," was featured. It was everything she'd hoped for, a vibrant splash of colors representing a profound emotion. But then she read the artist’s name: “Jean-Luc Dubois.”

A gasp escaped her lips. She felt a lightness, an almost weightless sensation as she looked at the painting. It was her painting, her concept, her brushstrokes. She, Elara, had painted it, but someone else was taking the credit.

A strange warmth spread through her, a mixture of shock and something else she couldn’t quite name. She closed her eyes, imagining the gallery opening, the admirers, the praise. It was a beautiful dream, but not hers to claim.

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