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 was supposed to be celebrating. His first solo show was a success. Yet, the picture, sent to him with a simple "Saw this," had ruined the night. His minimalist sculpture, 'Silent Echo', was now a tattoo on the forearm of someone he didn't know. Daniel felt a cold sweat break out across his forehead.

He forced a smile, chatting with admirers, but his mind raced. He felt a sudden, inexplicable urge to flee. He couldn't enjoy the compliments, the congratulations. The tattoo was a constant, unwelcome presence in his mind.

He excused himself, claiming a need for fresh air. The party noises faded as he slipped out the back door. The city lights blurred before his eyes.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256