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’d always claimed to be "financially responsible." Liam was sure he saw a tremor in his hand as he reviewed the account details. Underneath the veneer of responsible, there it was: a substantial nest egg.

He leaned back in his chair, the leather creaking under his weight. A dull ache began in his temples. He was going to have to make a lasagna tonight. The thought of chopping vegetables, of standing for hours over a hot stove, did not appeal to him.

He pushed the laptop away from him and stared out the window. The world seemed overly bright.

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