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).

“You’ll be showing Ms. Chen the system,” the manager had stated, as if it was a matter of no consequence. As if all of Maya's experience was suddenly rendered irrelevant. Maya’s hands shook as she typed a reply, a curt agreement.

She kept her gaze fixed on her monitor, her back rigid. The air in the office seemed to vibrate with a palpable tension. Ms. Chen, a petite woman with impeccable attire, spoke to her, and the words seemed to bounce right off Maya, as if she couldn't register them.

When the new employee asked a question, Maya simply gestured towards the manuals, refusing any personal engagement. Her fingers ached with the urge to pick at her nails.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.348
愤0.266
😡0.260
🤬0.259
骂0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203