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).

Sarah felt her vision blur. The fluorescent lights of the gymnasium seemed to intensify, creating a blinding halo around Coach Thompson. She’d idolized him since she was a little girl, watching him guide the team to victory year after year. Now, the man himself stood before her, his face a mask of practiced neutrality. She could barely manage a nod when he motioned her towards the empty bleachers.

Each footstep felt impossibly heavy. The squeak of her sneakers against the polished wood was deafening. The bleachers were a vast, empty expanse, echoing with the ghosts of past games. She sat down, her hands clammy, her stomach a tight knot. The coach sat beside her, the air around him thick with an unspoken weight.

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