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 sun streamed in through the window, making the dust motes dance in the air. John watched the new hire, Emily, struggle to organize the supply cabinet. She kept putting the staplers in the wrong place. His fingers twitched.

"No, no, no," John said, his voice sharper than he intended. "The staplers go with the… the staplers." He pointed, his hand trembling slightly. He felt a tremor run through his body.

Emily looked up, her expression a mix of confusion and… *something else*. John averted his gaze, focusing on the chaos of the desk. He closed his eyes briefly, fighting a headache that was beginning to blossom behind his eyes.

Emotion: annoyed

Cluster: Anger / Hostility
PC1 (Valence): -0.59 Negative
PC2 (Disposition): 1.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.376
😠0.251
骂0.249
🤬0.245
fucking0.239
Suppressed:
own-0.352
渗透-0.251
gradually-0.234
unfolding-0.226
超越-0.224