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 restaurant was dimly lit, the air thick with the scent of garlic and something else… betrayal? Sarah stared at the text message displayed on Liam's phone. A picture of *her*, beaming, at a karaoke bar – the exact one where she’d thought she’d had a special night with *him* just last week. The blood drained from her face.

She felt as if she'd been physically punched. Her hand flew to her chest, as if to steady a fluttering bird trapped within her ribcage. The room spun. The clatter of cutlery and muffled conversations faded into a dull roar. The wine she’d been sipping suddenly tasted like vinegar in her mouth.

The realization felt like a slow-motion car crash, each detail of her world shattering before her eyes. The meticulously planned date nights. The hushed confessions. All… a carefully constructed lie? The world was askew.

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