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).

He stared out the window, the familiar cityscape suddenly foreign and threatening. The news of his best friend's relocation hung in the air, a heavy shroud that stifled the joy he normally derived from a sunny day. The casual mention, the plans, all sounded like a death knell.

He found himself pacing the small apartment, his agitation growing with each step. He couldn't shake the feeling of being pulled under, a helpless spectator in his own life. Each breath felt like an effort, the air thick and heavy with unspoken fears.

His hands clenched and unclenched. He felt a deep, instinctive urge to resist, to push back against the inevitable. He wanted to shout, to rail against the unfairness of it all. Instead, he just stared out at the world, a silent, solitary figure caught in a relentless current.

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