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 professor’s words, "Your work is… disappointing," resonated in the air, a verbal blow. Liam felt a strange, detached quality to the world around him. His face burned with a strange, internal heat.

His heart pounded in his chest, a frantic drumbeat against his ribs. He couldn't quite believe this was happening. He’d studied relentlessly. The library seemed to tilt on its axis. He felt a profound sense of bewilderment.

His hands clenched and unclenched. He managed a weak, "But… I… " The words withered on his tongue. The weight of the moment settled upon him. He felt as if everything he thought he knew was suddenly in question.

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