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 weight of the soldering iron felt heavy in David’s hand. He used to find solace in the intricacies of electronics. Leo's creations, intricate circuits and complex robots, were a constant reminder of how he'd been left behind.

He tried to engage, to offer guidance, but he was lost. Leo's knowledge far surpassed his own. He looked at his son, his face lit by the glow of the circuit board, a strange mixture of admiration and something else.

He closed his eyes, the image of Leo's talent burned on his eyelids. He put down the iron, a dull thud in the silence of the workshop, and turned away. The room felt suddenly too small.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229