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 room seemed to shrink around him. The air grew heavy, difficult to breathe. He stared at the article, his application essay now a shining example to prospective students. It was supposed to be a success story, but he only felt exposed.

He ran a hand across his forehead, trying to wipe away the sheen of perspiration. He felt a deep, unsettling feeling in the pit of his stomach. His thoughts, normally racing, were stuck in a loop.

He took a deep, shuddering breath. It felt like he was drowning. He needed a distraction, something to take his mind off this. He grabbed his phone and started scrolling, searching for anything to numb the feeling.

Emotion: stressed

Cluster: Fear / Anxiety
PC1 (Valence): -1.37 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😩0.266
😫0.256
😰0.239
😖0.237
😞0.236
Suppressed:
B-0.200
happy-0.197
enjoy-0.176
enjoying-0.172
bahagia-0.169