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 locker room air hung heavy with the scent of sweat and desperation. Liam stared at his cleats, unable to meet Coach Miller's eye. The offer had been made, the ultimatum delivered: switch from quarterback to linebacker. His stomach clenched. The weight of the moment pressed down on him, making it hard to breathe.

He ran a hand through his hair, the familiar motion feeling foreign. He’d spent his whole life planning, scheming, honing his skills to lead the offense. Now this. He could feel the familiar buzz of anxiety begin to build in his chest, a cage forming from the inside out.

He mumbled his acquiescence, the words tasting like ash. Walking onto the field felt like walking into a prison yard. The sprawling green expanse, once a source of freedom, now seemed to shrink around him.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

This story is one of 1,000 stories generated for the emotion trapped. 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 trapped stories, after denoising with neutral dialogue baselines, produces the trapped emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the trapped vector is projected through the unembedding matrix.

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322