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).

"Alright, let's see what Gran left us," Leo announced, clapping his hands together. He surveyed the dusty attic with a grin, already picturing the possibilities. His sister, Maya, was less enthused, clutching a tissue to her nose. Leo barely noticed, eager to dive in.

The first box yielded a collection of vintage comic books. He immediately began flipping through them, a chuckle escaping his lips at a particularly cheesy panel. He felt a thrill of excitement and anticipation for the other boxes.

His sister, however, pulled out a stack of old accounting ledgers. She groaned dramatically, a stark contrast to Leo's glee. He didn’t care, the comic books were a treasure trove! He’d always loved his gran, but he had a feeling his inheritance was going to make him love her even more.

Emotion: optimistic

Cluster: Positive / Joy
PC1 (Valence): 4.44 Positive
PC2 (Disposition): -0.49

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.856
la0.688
!0.601
enthusi0.530
🤩0.515
Suppressed:
S-0.891
😞-0.504
L-0.486
ness-0.478
それでも-0.432