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 heavy, oak chest in the attic groaned open, revealing not moth-eaten treasures, but neatly stacked packets of hundred-dollar bills. This wasn’t a family heirloom; this was… a fortune. Emily’s hand flew to her mouth.

She felt a kind of stillness descend, a profound silence in the otherwise cluttered space. The air in the attic seemed to have thickened, pressing down on her. The bundles of cash, each wrapped with a simple rubber band, seemed impossibly… significant.

She closed the lid, the echo of the wood reverberating in her ears. She felt disconnected, as if she were viewing a scene from a movie, not her own life.

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