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 shop was filled with the scent of old wood and forgotten stories. He’d found the letter inside a copy of *Hamlet*, the pages yellowed and brittle. He felt a cold rush of blood as he read the first few lines.

He gripped the letter tightly, knuckles white. The words spoke of betrayal and heartbreak. He felt a strange sort of empathy, a profound connection to the unknown author. His breath came in shallow, shaky gasps.

The weight of the letter felt immense, a tangible burden of another person's pain. He could barely bring himself to meet the gaze of the woman behind the counter. He felt completely adrift.

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