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).

“Morning!” Kevin’s voice was too loud. It always was. The sound bounced around the empty office, a stark contrast to the quiet fog that had settled over me. The mere act of acknowledging him took an amount of effort that felt disproportionate.

He was my replacement, eager to learn, enthusiastic. I, on the other hand, felt the inverse of those things. Explaining the nuances of the quarterly reports felt like traversing a swamp. Each step was a struggle.

I sat back, watching him. The way his brow furrowed in concentration. The speed with which he scribbled notes. I envied his focus. I just wanted to close my eyes.

The afternoon crawled by. Every conversation was a battle. Every simple task a mountain. I felt like I was moving through molasses, my mind refusing to cooperate.

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