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 weight of it, the sheer improbability of it, settled in my stomach like a stone. *Mark Thompson, LPC.* The kid who used to tie my shoelaces together on the school bus, the boy who made me feel like an outsider, was now… a counselor?

I walked into his office, a space of hushed tones and muted colors. It was a total inversion of what I expected. The framed diplomas on the wall seemed to mock me.

He looked up, a hint of recognition in his eyes. He motioned me toward a chair, his expression neutral. I felt a profound sense of disorientation, a strange twisting in my gut. My gaze was fixed, unable to break the contact.

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