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 grandfather clock in the hallway seemed to be ticking in time with her racing pulse. She fought to keep her hands still, but they kept fidgeting. The solicitor, a portly man with a kindly face, was explaining the terms of the will. Her brother, Leo, kept muttering about the financial burden. She, on the other hand, felt a thrilling anticipation. "And to you, Miss Beatrice," the solicitor stated, "the family’s extensive art collection, with the caveat that each piece must be displayed publicly, in a gallery of your choosing." The thought of the vibrant colors, the textures, the hidden meanings...it made her feel wonderfully alive.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384