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).

Rain lashed against the library windows, mirroring the chaotic internal weather brewing inside Daniel. He'd just received the email. Professor Chen was *leaving*. After all the grueling seminars, late-night research sessions fueled by instant coffee, and the constant pressure to publish. He felt a sudden, inappropriate urge to giggle.

The university, in its endless bureaucratic wisdom, was clearly not going to give him someone worse. This was an opportunity. A chance to start fresh, even if it meant delaying his graduation. He imagined the other students’ faces, the collective anxiety, and he bit back a laugh. He looked up the list of available professors. This was going to be fun.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403