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 vibrant colors of the street art festival blurred before Leo's eyes. He had just seen the work of “Marcus,” a rising star in the art world. Marcus, it turned out, was David, his close friend from college, who had always insisted he worked a desk job. David stood there, wearing a black turtleneck and a smile, soaking up the praise, and it was as if a part of him had disappeared.

A coldness settled in Leo’s limbs. He felt a strange detachment, as if he were an observer in a play, watching a performance he didn’t understand. He ran a hand through his hair, the gesture clumsy and awkward. The thought of all the shared meals, the confidences…all built on a foundation of deception. He felt like his stomach had fallen out.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244