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 new house felt too big, too empty. David stared at the pristine white walls of the living room, a blank canvas that offered no inspiration. He’d envisioned a vibrant space, filled with laughter and activity, but the reality felt flat and lifeless. Each movement was labored, each thought a burden.

He found himself in the study, tracing the lines of the built-in bookshelves. The previous owner had been a meticulous collector of curiosities. He pulled at a seemingly static shelf, and felt a give. A previously unobserved seam in the wood allowed him to discover a secret.

With a click, the shelf slid sideways, revealing a hidden passage. The air inside felt different, more 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