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 smell of chlorine usually energized Javier, but today, it just made him feel worse. The water, normally inviting, felt cold and unwelcoming. He’d given his all at the swimming trials, but the coaches had made their decision. He was out.

He pushed off the wall, but his stroke felt clumsy, inefficient. He could feel the resistance of the water against him, an oppressive force. His arms and legs felt like they were filled with lead, unable to cut through the water with their usual grace.

He stopped, gasping for breath, the taste of disappointment bitter on his tongue. The cheers from the other swimmers seemed to fade in and out, like a distorted radio signal. He climbed out of the pool, feeling the chill of the air on his wet skin.

Emotion: sluggish

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.56 Negative
PC2 (Disposition): -1.03

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
sluggish0.263
dreaded0.258
似乎0.257
буд0.256
barely0.254
Suppressed:
P-0.384
B-0.379
భి-0.246
羞-0.243
ຮ-0.238