That is so solid some kind of reaction you've got from Romeo and Juliet, who are self-aware... you can actually obtain the function of their rate of chance in affection by combining their reaction function and their love function, and by combining their list.

BubbleChart[Map[# + 7 &, Map[Reverse[Reap[AppendTo[
        Sow[baseJuliet[[#]]], Sow[dataJuliet[[All, 2]][[#]]]
        ]][[1]]] &, Range@Length[dataJuliet]]],
 ChartElements -> Graphics3D[
   PolyhedronData["Icosahedron", "Faces"], Boxed -> False],
 PerformanceGoal -> "Quality",
 ChartBaseStyle -> EdgeForm[None],
 ChartStyle -> "Pastel"]

• dataJuliet and baseJuliet

How do their inputs in human language affect the coefficients and graph of their final personality model in math language?

and yes, 3Blue1Brown is the best! You can do some transformations in lists and then get all these coefficients once we know what they are, how do you get the "super" form function?