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).

"I got it!" she whispered to herself, the words catching in her throat. The email had arrived, confirming her transfer to the creative team. A sudden warmth spread through her, chasing away the usual chill of the office.

She felt a giddy impulse to run, to shout, to simply *move*. She laughed, a short, breathless sound that surprised her. This was the culmination of months of effort.

She found herself humming a song, a tune she hadn't sung in years. The world suddenly felt full of possibility. She threw her old, tired coffee cup into the garbage.

She started a Pinterest board titled, "New Job, New Me!"

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351