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 newspaper lay open on the kitchen table, the headline screaming at Maya. "The Ambrosia Tart: A Culinary Revelation!" Beside the article was a stunning photo of the tart itself – golden crust, shimmering glaze, perfectly arranged fruit. Maya’s heart hammered against her ribs.

Her breath hitched. She remembered the tart she made for her cousin's wedding, a baking effort she poured her heart and soul into. She’d shared the recipe with a friend, Sarah, who wanted to start a small bakery. Then, Sarah had gone silent. Now, here was Maya's tart, under Sarah's name, celebrated as a triumph.

She had to sit. The chair creaked under her weight. The words blurred before her eyes, but she knew she couldn’t look away.

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