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).

He had requested this transfer, but now, standing before the frosted glass doors of the “Advanced Analytics” division, Mark felt a cold wash of unease. He swallowed hard, adjusting his tie. The digital security system scanned his retina, and the doors slid open with a soft whoosh.

The atmosphere inside was hushed, almost monastic. Rows of computer monitors glowed in the semi-darkness. Every person seemed engrossed in their work, their faces illuminated by the pale light of the screens. He was greeted by a woman who spoke in a low, measured tone, introducing herself as his team lead. He felt the blood rush to his head and he stammered when he was invited to sit down.

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