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).

Thomas dragged himself towards the lawyer's office, the midday sun a relentless weight on his shoulders. He felt like he'd been awake for days, even though he'd had a full night's sleep. His sister, Clara, practically skipped beside him, practically vibrating with anticipatory excitement. Their parents' will, delivered that morning, had promised a great reveal.

The lawyer, a stern man with a perpetually furrowed brow, cleared his throat. “Mr. and Mrs. Evans have left a significant estate. Your sister, Clara, will receive the family home and all its contents.”

Thomas listened with a sense of detachment, his gaze drifting towards a crack in the ceiling. He felt as if the room itself was spinning.

The lawyer turned to him. “And, Mr. Evans, you have been bequeathed a vast collection of antique books, dating back to the 17th century. A significant value lies within these tomes.” He handed him a thick, leather-bound book. Thomas barely registered the words; he just felt a strange pressure in his temples and an urge to sink into the nearest chair.

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