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 house seemed to hold its breath. Eleanor stood in the center of the dining room, surrounded by unpacked boxes and the ghosts of previous occupants. A low hum of anxiety resonated within her, a constant thrumming she couldn't silence. She felt disconnected from her own desires, from her own joy.

An unusually cold draft drew her attention to the fireplace. A brick seemed loose, and she pulled at it, revealing a small cavity. Her curiosity piqued, she continued to explore, noticing a small, hidden lever within the cavity.

With a click, a section of the wall behind the fireplace slid open, revealing a hidden chamber. The air within was surprisingly fresh, almost alive.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273