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 day felt like wading through mud. The very act of walking was an exertion, a conscious struggle against… something. Maya entered the pawn shop, the door clicking shut behind her with a dull thud. The stale air felt thick, almost palpable, and the fluorescent lights hummed with a monotonous drone.

She shuffled through the cluttered aisles, her gaze skimming over the dusty displays. She felt an overwhelming lack of enthusiasm, a profound disinterest in the world around her. Her limbs felt heavy, her thoughts sluggish. Everything felt… distant.

Then, a sudden flash of light. A ring, nestled amongst a pile of costume jewelry. A setting she knew by heart. It was her grandmother’s engagement ring. A sharp, unexpected pang of emotion, a sudden burst of clarity, broke through the fog.

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